Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Generative Path-Finding Method for Wasserstein Gradient Flow
Chengyu Liu, Xiang Zhou
Wasserstein gradient flows (WGFs) describe the evolution of probability distributions in Wasserstein space as steepest descent dynamics for a free energy functional. Computing the…
cs.LG2024
Weak Generative Sampler to Efficiently Sample Invariant Distribution of Stochastic Differential Equation
Zhiqiang Cai, Yu Cao, Yuanfei Huang +1
Sampling invariant distributions from an Itô diffusion process presents a significant challenge in stochastic simulation. Traditional numerical solvers for stochastic differential…